FedTriNet: A Pseudo Labeling Method with Three Players for Federated Semi-supervised Learning

TL;DR

FedTriNet is a federated semi-supervised learning approach that employs three networks and a dynamic quality control mechanism to generate high-quality pseudo labels, improving model performance on distributed unlabeled data.

Contribution

The paper introduces FedTriNet, a novel federated semi-supervised learning method with a three-network pseudo labeling strategy and dynamic quality control, addressing unlabeled data challenges.

Findings

Outperforms state-of-the-art baselines on three datasets.

Effective in both IID and Non-IID data distributions.

Utilizes pseudo labels to leverage unlabeled data effectively.

Abstract

Federated Learning has shown great potentials for the distributed data utilization and privacy protection. Most existing federated learning approaches focus on the supervised setting, which means all the data stored in each client has labels. However, in real-world applications, the client data are impossible to be fully labeled. Thus, how to exploit the unlabeled data should be a new challenge for federated learning. Although a few studies are attempting to overcome this challenge, they may suffer from information leakage or misleading information usage problems. To tackle these issues, in this paper, we propose a novel federated semi-supervised learning method named FedTriNet, which consists of two learning phases. In the first phase, we pre-train FedTriNet using labeled data with FedAvg. In the second phase, we aim to make most of the unlabeled data to help model learning. In particular, we propose to use three networks and a dynamic quality control mechanism to generate high-quality pseudo labels for unlabeled data, which are added to the training set. Finally, FedTriNet uses the new training set to retrain the model. Experimental results on three publicly available datasets show that the proposed FedTriNet outperforms state-of-the-art baselines under both IID and Non-IID settings.